© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49636
    Prev
    Next
    INDEX
    Explanations

    date format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dalton
    -0.10
    angler
    -0.09
    idar
    -0.09
    lash
    -0.09
    odon
    -0.09
    nable
    -0.09
    laces
    -0.09
     lem
    -0.09
    IRM
    -0.08
     crank
    -0.08
    POSITIVE LOGITS
     Carr
    0.10
     realistic
    0.09
     metall
    0.09
     exhaust
    0.09
    vit
    0.09
     vit
    0.09
     ave
    0.09
     worthwhile
    0.09
     tres
    0.09
     Siege
    0.09
    Activations Density 0.089%

    No Known Activations